Thermal imagery is emerging as a viable candidate for 24-7, all-weather pedestrian detection owning to thermal sensors’ robust performance for pedestrian detection under different weather and illumination conditions. Despite the promising results obtained from combining visible (RGB) and thermal cameras in multi-spectral fusion techniques, the complex synchronization requirements, including alignment and calibration of sensors, impede their deployment in real-world scenarios. In this paper, we introduce a novel approach for domain adaptation to enhance the performance of pedestrian detection based solely on thermal images. Our proposed approach involves several stages. Firstly, we use both thermal and visible images as input during the training phase. Secondly, we leverage a thermal-to-visible hallucination network to generate feature maps that are similar to those generated by the visible branch. Finally, we design a transformer-based multi-modal fusion module to integrate the hallucinated visible and thermal information more effectively. The thermal-to-visible hallucination network acts as domain adaptation, allowing us to obtain pseudo-visual and thermal features using solely thermal input. Based on the experimental results, it is observed the mean average precision (mAP) increases by 4.72% and the miss rate decreases by 7.56% on the KAIST dataset when compared to the baseline model.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Illumination-Aware Hallucination-Based Domain Adaptation for Thermal Pedestrian Detection


    Beteiligte:
    Xie, Qian (Autor:in) / Cheng, Ta-Ying (Autor:in) / Dai, Zhuangzhuang (Autor:in) / Tran, Vu (Autor:in) / Trigoni, Niki (Autor:in) / Markham, Andrew (Autor:in)


    Erscheinungsdatum :

    2024-01-01


    Format / Umfang :

    1640582 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Uncertainty-Aware Pseudo Labels for Domain Adaptation in Pedestrian Trajectory Prediction

    Poibrenski, Atanas / Nozarian, Farzad / Rezaeianaran, Farzaneh et al. | IEEE | 2023


    Unreliability-Aware Disentangling for Cross-Domain Semi-supervised Pedestrian Detection

    Wu, Wenhao / Wu, Si / Wong, Hau-San | British Library Conference Proceedings | 2023


    Facial Expression Hallucination

    Su, Congyong / Huang, Li | IEEE | 2005


    Face Hallucination: Theory and Practice

    Liu, C. / Shum, H. Y. / Freeman, W. T. | British Library Online Contents | 2007


    Thinking Hallucination for Video Captioning

    Ullah, Nasib / Mohanta, Partha Pratim | British Library Conference Proceedings | 2023